基于高光谱图像技术的油炸薯片中羧甲基赖氨酸含量检测  

Detection of N^(ε)-(1-Carboxymethyl)-L-Lysine Content in Fried Potato Chips Based on Hyperspectral Imaging

作　　者：王润博 韩文凤 于慧春[3] WANG Run-bo;HAN Wen-feng;YU Hui-chun(Luohe Institute of Industry,Henan University of Technology,Luohe 462000,Henan,China;Jianhu University,Zhejiang Industry Polytechnic College,Shaoxing 312000,Zhejiang,China;College of Food&Bioengineering,Henan University of Science and Technology,Luoyang 471023,Henan,China)

机构地区：[1]河南工业大学漯河工学院,河南漯河462000 [2]浙江工业职业技术学院鉴湖学院,浙江绍兴312000 [3]河南科技大学食品与生物工程学院,河南洛阳471023

出　　处：《食品研究与开发》2022年第8期152-159,共8页Food Research and Development

基　　金：河南省科技攻关项目(172102110222)。

摘　　要：为探究羧甲基赖氨酸[N^(ε)-(1-carboxymethyl)-L-lysine,CML]含量的快速无损检测方法,该文采用高光谱图像技术对8种自制油炸薯片进行检测研究,提取每个高光谱图像的平均光谱值作为特征参量,同时结合液相色谱-质谱法测定CML含量,探寻预测其含量最适宜的光谱预处理和建模方法。首先将高光谱图像进行黑白校正,再选用标准正态变量变换光谱预处理方法,以消除固体颗粒、散射以及光程变化对光谱的影响。然后筛选出第200个到1 000个波段图像的平均光谱反射值,建立主成分回归、偏最小二乘回归和BP神经网络3种预测模型。对比结果表明:BP神经网络可以预测油炸薯片中CML含量,预测正确率为99.67%,决定系数为0.99,均方根误差为0.22。同时,为验证模型的稳健性,随机选取5组训练集和预测集代入相同参数的模型进行预测。结果显示:预测正确率平均值为96.23%,决定系数平均值为0.99,均方根误差平均值为0.22。这说明高光谱图像技术结合BP神经网络快速预测油炸薯片中CML含量具有可行性。This study aims to explore a method for the fast and nondestructive detection of [N^(ε)-(1-carboxymethyl)-L-lysine(CML)]. Hyperspectral imaging technology was employed to detect 8 kinds of homemade fried potato chips and the average spectral value of each hyperspectral image was extracted as the feature parameter. Meanwhile,the content of CML was determined by liquid chromatography-mass spectrometry(LC-MS). The suitable spectral pretreatment and modeling method were then explored. Firstly,the black-and-white correction was carried out for hyperspectral images. Secondly,standard normal variable transformation was used to eliminate the influence of solid particles,scattering and optical path change on spectrum. Thirdly,the average spectral reflectance values from images at the 200;-1 000;wavebands were taken as the characteristic parameters for the building of three prediction models based on principal component regression,partial least squares regression and BP neural network,respectively. The comparison demonstrated that BP neural network had the prediction accuracy of 99.67%,the determination coefficient of 0.99 and the root mean square error of 0.22. Furthermore,five groups of training set and prediction set were randomly selected to verify the model robustness. The result showed that the average prediction accuracy,determination coefficient and root mean square error was 96.23%,0.99 and 0.22,respectively. Therefore,it is feasible to combine the hyperspectral imaging technology with BP neural network for the rapid prediction of CML content in fried potato chips.

关 键 词：高光谱图像 主成分分析 偏最小二乘 BP神经网络 油炸薯片 羧甲基赖氨酸(CML) 

分 类 号：TS215[轻工技术与工程—粮食、油脂及植物蛋白工程]